arXiv AI
Aug 5
Risky Business: Measuring The Faithfulness-Safety Tension
arXiv:2608. 03745v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning offers a promising window into model monitoring.
Towards Understanding the Cognitive Habits of Large Reasoning Models
arXiv:2506. 21571v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs), which autonomously produce a reasoning Chain of Thought (CoT) before producing final responses, offer a promising approach to interpreting and monitoring model behaviors.
Related stories
arXiv AI
Aug 25
Cognitive Profiling of LRMs' Reasoning Traces Using Bloom's Taxonomy
arXiv:2608.23205v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have revolutionized reasoning in LLMs, and the increasing public availability of reasoning traces creates valuable opport...
arXiv AI
Sep 3
When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning
The paper investigates why large reasoning models (LRMs) often continue to think even when prompted to stop, a phenomenon called "Still-thinking". By examining confidence at the thinking-termination boundary, internal attention divergences, and attention allocation across prompt segments, the authors find that high perplexity and greater attention to the original question correlate with continued thinking. They propose an attention‑intervention method that suppresses explicit reasoning, which reduces inefficiency but also lowers accuracy, underscoring a trade‑off between instruction compliance, inference speed, and correctness.
arXiv AI
Aug 3
On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
arXiv Computation and Language
Sep 1
Detecting Hidden Chain-of-Thought in Large Language Models with Linguistic, Behavioral, and Mechanistic Indicators
arXiv:2608.29956v1 Announce Type: new Abstract: Large language models often answer complex reasoning questions without revealing intermediate steps, raising whether they reason latently or complete p...
arXiv AI
Jun 2
An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
arXiv:2606. 01462v1 Announce Type: new Abstract: Studies of human reasoning have shown that people are typically stronger at evaluating reasoning than producing it from scratch.
arXiv AI
Sep 15
Thought without systematicity? Evaluating reasoning models on rule induction tasks
The paper investigates whether current reasoning models exhibit systematicity—the idea that understanding one concept should extend to closely related variations—by extending rule induction tasks from cognitive science. Using task isomorphisms like recombination and substitution, the authors generate structurally equivalent task variants and test models on them. Results show that while models can solve the original tasks, they frequently fail on these equivalent variants, indicating a lack of systematicity in their reasoning abilities.
arXiv AI
Aug 17
Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models
arXiv:2608. 13760v1 Announce Type: cross Abstract: Which reasoning behaviors are associated with correct answers in reasoning models, and does reasoning-oriented training amplify those behaviors?
arXiv AI
Aug 11
Understanding and Mitigating Premature Confidence for Better LLM Reasoning
arXiv:2605. 24396v2 Announce Type: replace Abstract: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute.
arXiv AI
Aug 10
Counterfactual Simulation Training for Chain-of-Thought Faithfulness
arXiv:2602. 20710v2 Announce Type: replace Abstract: Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM produced its output.
arXiv AI
Sep 3
Thinking effort aligns between humans and reasoning models in abductive reasoning
The study examines how the effort expended by large reasoning models (LRMs) compares to that of humans during abductive reasoning tasks. By analyzing reaction times and reasoning traces, the authors find that LRMs and humans exhibit similar patterns of effort and error types. They also demonstrate that decoding strategies allowing models to explore multiple reasoning paths further align the models’ reasoning costs with human effort.
arXiv AI
Jun 26
Humans Disengage, Reasoning Models Persist: Separating Difficulty Registration from Deliberation Allocation
arXiv:2606. 26502v1 Announce Type: new Abstract: Large reasoning models (LRMs) take longer on harder problems, just as humans do.